Energy-Delay Tradeoff for Dynamic Trajectory Planning in Priority-Oriented UAV-Aided IoT Networks
Hailin Cao, Zhu Wang, Zhengchuan Chen, Zhiwei Sun, Dapeng Wu
Abstract
Unmanned aerial vehicles (UAVs) play a crucial role in emergency-oriented applications. However, in UAV-aided Internet of Things (IoT) networks, the sensor nodes (SNs) would be mobile which poses a big challenge for trajectory planning of the UAV. In this paper, we investigate priority-oriented UAV-aided time-sensitive data collection problems in an IoT network with movable SNs. By defining different levels of delay sensitivities for each SN, we jointly minimize the energy consumed by a UAV and the average delay of different SNs through optimizing the trajectory of the UAV. The problem is formulated as a multi-objective optimization problem (MOP). To solve the formulated problem, we first transform the MOP into a single-objective optimization problem based on the weighted sum method. Then, we propose a novel autofocusing heuristic trajectory planning algorithm based on reinforcement learning (AHTP-RL) which can be operated in an online manner. The proposed algorithm can well extract the network dynamic topology and the delay-priority of SN through an attention mechanism, hence can structure the UAV’s trajectory efficiently. Extensive simulations results demonstrate that the proposed online AHTP-RL algorithm can achieve a superior balance between the communication delay and energy consumption for both low and high SN mobilities.